Evaluation data
Term · Chemistry · MLC-T-CHM-004128
A set of observations, also called validation data, kept for judging how well a fitted model predicts; it must be independent of the samples used to build the model by calibration or training. A root mean square error computed on these data is a standard measure of predictive ability. Test data, by contrast, are measurements on unknown samples, and the name is not applied to evaluation data.
| Identifier | MLC-T-CHM-004128 |
|---|---|
| Field | Chemistry |
| Subject | Analytical Chemistry |
| Synonyms | validation data |
| References | PAC, 2016, 88, 407. 'Vocabulary of concepts and terms in chemometrics (IUPAC Recommendations 2016)' on page 410 (https://doi.org/10.1515/pac-2015-0605) |
| See also | Model |
Record as JSON
{
"id": "MLC-T-CHM-004128",
"term": "Evaluation data",
"field": "Chemistry",
"definition": "A set of observations, also called validation data, kept for judging how well a fitted model predicts; it must be independent of the samples used to build the model by calibration or training. A root mean square error computed on these data is a standard measure of predictive ability. Test data, by contrast, are measurements on unknown samples, and the name is not applied to evaluation data.",
"synonyms": [
"validation data"
],
"subject": "Analytical Chemistry",
"see_also": [
"model"
],
"references": [
"PAC, 2016, 88, 407. 'Vocabulary of concepts and terms in chemometrics (IUPAC Recommendations 2016)' on page 410 (https://doi.org/10.1515/pac-2015-0605)"
],
"url": "https://mlchart.com/terminology/chemistry/evaluation-data/"
}
Record 4,376 of 13,676 in Chemistry terminology (MLC-0109). Request the full dataset.